AIBullisharXiv – CS AI · May 127/10
🧠
EvoMAS: Learning Execution-Time Workflows for Multi-Agent Systems
Researchers introduce EvoMAS, a framework that dynamically constructs multi-agent workflows during task execution rather than using static, pre-optimized designs. The system uses a Planner-Evaluator-Updater pipeline to assess task state and adapts agent coordination across execution stages, demonstrating superior performance on complex reasoning tasks compared to existing approaches.